Mindforge

io.github.sairam0424Published by GitHub account sairam0424v11.9.8Updated Oct 24, 2026

Read the MindForge engine over MCP: knowledge graph, project health, and audit log.

VerifiedSTDIODesktop onlyBrowser AutomationKnowledge & Memory

Overview

AI-generated overview

A local stdio MCP server that lets an assistant read a MindForge project's knowledge graph, health, status and audit log, and append new knowledge entries.

What you can do
Check project health and read initialization status, active phase and handoff state for the current project. Search the SQLite-backed knowledge graph by topic, tags and type, and find related entries from free text via hybrid retrieval. Report knowledge-graph statistics such as entry counts, types and tag distribution. Read entries from the tamper-evident audit log, optionally filtered by event. Append a new knowledge entry (decision, pattern or preference) to the graph. Drive an already-running MindForge browser daemon for status, navigation, clicks, typing, screenshots and assertions.
When to use it
Useful when working in a project set up with MindForge and you want the assistant to consult recorded decisions, patterns and preferences, check project health, or review the audit trail without leaving the session.
Requirements
Runs locally over stdio, typically via npx from the npm package mindforge-mcp-server; Node.js is needed for npx. The project must contain MindForge's .mindforge/ and .planning/ directories. Set CLAUDE_PROJECT_DIR to the project path; it defaults to the current working directory. The browser tool needs a MindForge browser daemon already running.
Before you install
The memory-remember tool writes new entries into the project's knowledge graph, and the browse tool can navigate, click and type in a browser, which sends data to third-party sites. The server scopes operations to CLAUDE_PROJECT_DIR and talks only to the local loopback address, but the separate browser daemon performs actual network egress. Tools return messages rather than failing when MindForge is not initialized.

Installation

In SourceWeft

  1. Open Mindforge in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

mindforge-mcp-server

Read the MindForge engine — knowledge graph, project health, and audit log — from Claude Code or any MCP host, over stdio.

[npm version] [License: MIT]

A self-contained Model Context Protocol (MCP) server that exposes the MindForge engine to AI agents: query the SQLite-backed knowledge graph, find related memory, check project health, and read the tamper-evident audit log — plus one guarded write to persist new knowledge. Zero runtime dependencies (the server and its deps are bundled into a single file), so it runs on a clean install, offline, and on first session.

Install

bash
claude mcp add mindforge -- npx -y mindforge-mcp-server

Or add it manually to your MCP host config (Claude Desktop, Cursor, VS Code):

json
{  "mcpServers": {    "mindforge": {      "command": "npx",      "args": ["-y", "mindforge-mcp-server"],      "env": { "CLAUDE_PROJECT_DIR": "${workspaceFolder}" }    }  }}

The server scopes every operation to CLAUDE_PROJECT_DIR (the project containing .mindforge/ and .planning/). If unset, it falls back to the current working directory. Every tool degrades gracefully with an actionable message when MindForge is not initialized in the project — it never throws.

Tools

ToolAccessDescription
mindforge_healthread-onlyRun a MindForge health check on the current project (config, state, knowledge graph, audit chain).
mindforge_statusread-onlyRead current project status: whether MindForge is initialized, active phase, and handoff state.
mindforge_memory_queryread-onlySearch the knowledge graph (architectural decisions, patterns, preferences) by topic, tags, and type.
mindforge_memory_statsread-onlyReport knowledge-graph statistics: total/active entries, types, and tag distribution.
mindforge_memory_find_relatedread-onlyGiven free text, find related knowledge entries via hybrid (FTS5 + graph-traversal) retrieval.
mindforge_audit_logread-onlyRead entries from the tamper-evident audit log (.planning/AUDIT.jsonl), optionally filtered by event.
mindforge_memory_rememberwrite (guarded)Persist a new knowledge entry (decision, pattern, or preference) into the graph.
mindforge_browsewrite (guarded, open-world)Drive the MindForge browser daemon: status/navigate/click/type/screenshot/assert. Requires the daemon to already be running (/mindforge:browse --start); never spawns it, and never exposes JS eval or cookie import.

All tools are annotated with readOnlyHint / destructiveHint so MCP hosts can enforce the right trust boundary; only mindforge_memory_remember writes, and it is append-only.

Transport & security

  • Transport: stdio JSON-RPC (single embedded client).
  • Scope: read/append only within CLAUDE_PROJECT_DIR, plus a loopback-only proxy to the MindForge browser daemon (mindforge_browse) — no shell execution. The MCP server process itself only ever talks to 127.0.0.1; the daemon (a separate, pre-existing process this server never spawns) performs the actual browser network egress when a page navigates.
  • Self-contained: the SDK and Zod are bundled into dist/index.js; no node_modules are needed at runtime.

Part of MindForge

This server ships standalone (npm + MCP registries) and bundled inside the MindForge Claude Code plugin. For the full framework — slash commands, subagents, governance, and cost-aware model routing — see the main repository.

License

MIT © MindForge Team

Source: mcp-server/README.md at commit ce0a58d

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

2
  1. v11.9.8LatestSep 21, 2026
  2. v11.5.1Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts